{"id":"https://openalex.org/W4387171899","doi":"https://doi.org/10.3233/faia230415","title":"Theoretically Guaranteed Policy Improvement Distilled from Model-Based Planning","display_name":"Theoretically Guaranteed Policy Improvement Distilled from Model-Based Planning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171899","doi":"https://doi.org/10.3233/faia230415"},"language":"en","primary_location":{"id":"doi:10.3233/faia230415","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230415","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230415","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230415","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063854306","display_name":"Chuming Li","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Chuming Li","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021859761","display_name":"Ruonan Jia","orcid":"https://orcid.org/0000-0001-7068-4274"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruonan Jia","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454075","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0002-1782-2081"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732590","display_name":"Yinmin Zhang","orcid":"https://orcid.org/0000-0002-7736-5337"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Yinmin Zhang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089605411","display_name":"Yazhe Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yazhe Niu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090073634","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0001-8132-5613"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaodong Yang","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102513637","display_name":"Yu Liu","orcid":"https://orcid.org/0009-0006-7055-6524"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["AU","CN"],"is_corresponding":true,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087818121"],"corresponding_institution_ids":["https://openalex.org/I129604602","https://openalex.org/I4210100255","https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":2.1245,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90727485,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8018597364425659},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7301767468452454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5771934986114502},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5069265961647034},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5018105506896973},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.494252473115921},{"id":"https://openalex.org/keywords/futures-studies","display_name":"Futures studies","score":0.4492010474205017},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4100739061832428},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.407524049282074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3751172423362732},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2510311007499695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20034566521644592},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1914563775062561}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8018597364425659},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7301767468452454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5771934986114502},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5069265961647034},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5018105506896973},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.494252473115921},{"id":"https://openalex.org/C64848388","wikidata":"https://www.wikidata.org/wiki/Q188867","display_name":"Futures studies","level":2,"score":0.4492010474205017},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4100739061832428},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.407524049282074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3751172423362732},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2510311007499695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20034566521644592},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1914563775062561},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230415","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230415","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230415","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230415","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230415","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230415","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171899.pdf","grobid_xml":"https://content.openalex.org/works/W4387171899.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1906772730","https://openalex.org/W2087617385","https://openalex.org/W2121103318","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2736601468","https://openalex.org/W2770616710","https://openalex.org/W2781726626","https://openalex.org/W2785389871","https://openalex.org/W2787938642","https://openalex.org/W2789824229","https://openalex.org/W2805762288","https://openalex.org/W2810754397","https://openalex.org/W2859967432","https://openalex.org/W2902125520","https://openalex.org/W2950564923","https://openalex.org/W2950624398","https://openalex.org/W2963864421","https://openalex.org/W2964006217","https://openalex.org/W2996449210","https://openalex.org/W3092490845","https://openalex.org/W3130475119","https://openalex.org/W3134294674","https://openalex.org/W3209949248","https://openalex.org/W4225852029","https://openalex.org/W4288055195","https://openalex.org/W4288319859","https://openalex.org/W4297437261","https://openalex.org/W4298206671","https://openalex.org/W4298857966","https://openalex.org/W4364387564","https://openalex.org/W4389666640"],"related_works":["https://openalex.org/W2370236282","https://openalex.org/W3156023083","https://openalex.org/W4390453990","https://openalex.org/W1995047307","https://openalex.org/W3164313706","https://openalex.org/W4388907197","https://openalex.org/W2046413193","https://openalex.org/W4226108142","https://openalex.org/W2534881938","https://openalex.org/W2118564637"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4,106],"demonstrated":[5],"remarkable":[6],"successes":[7],"on":[8,168],"a":[9,107,132],"range":[10],"of":[11,26,54,60,66,80,103,110],"continuous":[12,170],"control":[13,171],"tasks":[14,173],"due":[15],"to":[16,33,88,93,115,137],"its":[17],"high":[18],"sample":[19,156],"efficiency.":[20],"To":[21],"save":[22],"the":[23,43,47,52,57,63,77,94,116,141],"computation":[24],"cost":[25],"conducting":[27],"planning":[28,55,92,166],"online,":[29],"recent":[30],"practices":[31],"tend":[32],"distill":[34,89],"optimized":[35],"action":[36],"sequences":[37],"into":[38],"an":[39,86,101],"RL":[40,61],"policy":[41,78,104,142],"during":[42],"training":[44],"phase.":[45],"Although":[46],"distillation":[48],"can":[49],"incorporate":[50],"both":[51,162],"foresight":[53],"and":[56,113,127,158,164],"exploration":[58],"ability":[59],"policies,":[62],"theoretical":[64,108],"understanding":[65],"these":[67],"methods":[68],"is":[69],"yet":[70],"unclear.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"extend":[76],"improvement":[79,105,112],"Soft":[81],"Actor-Critic":[82],"(SAC)":[83],"by":[84],"developing":[85],"approach":[87,102],"from":[90],"model-based":[91,165],"policy.":[95],"We":[96,122],"then":[97],"demonstrate":[98],"that":[99,152],"such":[100],"guarantee":[109],"monotonic":[111],"convergence":[114],"maximum":[117],"value":[118],"defined":[119],"in":[120,174],"SAC.":[121],"discuss":[123],"effective":[124],"design":[125],"choices":[126],"implement":[128],"our":[129],"theory":[130],"as":[131],"practical":[133],"algorithm\u2014Model-based":[134],"Planning":[135],"Distilled":[136],"Policy":[138],"(MPDP)\u2014that":[139],"updates":[140],"jointly":[143],"over":[144],"multiple":[145],"future":[146],"time":[147],"steps.":[148],"Extensive":[149],"experiments":[150],"show":[151],"MPDP":[153],"achieves":[154],"better":[155],"efficiency":[157],"asymptotic":[159],"performance":[160],"than":[161],"model-free":[163],"algorithms":[167],"six":[169],"benchmark":[172],"MuJoCo.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}